Volumetric efficiency modelling of internal combustion engines based on a novel adaptive learning algorithm of artificial neural networks

Abstract Air mass flow determination is one of the main variables on the control of internal combustion engines. Effectiveness of intake air systems is evaluated through the volumetric efficiency coefficient. Intake air systems characterization by means of physical models needs either significant amount of input data or notable calculation times. Because of these drawbacks, empirical approaches are often used by means of black-box models based on Artificial Neural Networks. As alternative to the standard gradient descendent method an adaptive learning algorithm is developed based on the increase of hidden layer weight update speed. The results presented in this paper show that the proposed adaptive learning method performs with higher learning speed, reduced computational resources and lower network complexities. A parametric study of several Multiple Layer Perceptron (MLP) networks is carried out with the variation of the number of epochs, number of hidden neurons, momentum coefficient and learning algorithm. The training and validation data are obtained from steady state tests carried out in an automotive turbocharged diesel engine.

[1]  Xiang-rong Li,et al.  Combustion and emission characteristics of a lateral swirl combustion system for DI diesel engines under low excess air ratio conditions , 2016 .

[2]  Hao Yu,et al.  Selection of Proper Neural Network Sizes and Architectures—A Comparative Study , 2012, IEEE Transactions on Industrial Informatics.

[3]  Xiangrui Zeng,et al.  A physics-based time-varying transport delay oxygen concentration model for dual-loop exhaust gas recirculation (EGR) engine air-paths , 2014 .

[4]  M. Mohanraj,et al.  Applications of artificial neural networks for refrigeration, air-conditioning and heat pump systems—A review , 2012, Renewable and Sustainable Energy Reviews.

[5]  Sven F. Crone,et al.  Cross-validation aggregation for combining autoregressive neural network forecasts , 2016 .

[6]  H. Climent,et al.  Heat transfer modeling in exhaust systems of high-performance two-stroke engines , 2014 .

[7]  S. Azizi,et al.  Prediction of heat transfer coefficient during condensation of R134a in inclined tubes using artificial neural network , 2016 .

[8]  F. Şahin,et al.  Effects of engine parameters on ionization current and modeling of excess air coefficient by artificial neural network , 2015 .

[9]  Kenji Fukumizu,et al.  Relation between weight size and degree of over-fitting in neural network regression , 2008, Neural Networks.

[10]  Changlu Zhao,et al.  Misfire detection of a turbocharged diesel engine by using artificial neural networks , 2013 .

[11]  John D. Hunter,et al.  Matplotlib: A 2D Graphics Environment , 2007, Computing in Science & Engineering.

[12]  Amir H. Shamekhi,et al.  A new approach in improvement of mean value models for spark ignition engines using neural networks , 2015, Expert Syst. Appl..

[13]  Hao Yu,et al.  Neural Network Learning Without Backpropagation , 2010, IEEE Transactions on Neural Networks.

[14]  Stefan Pischinger,et al.  NEURAL NETWORKS FOR MODELLING AND CONTROLLING FUTURE LOW TEMPERATURE COMBUSTION TECHNOLOGIES , 2007 .

[15]  Pascal Chesse,et al.  The Application of a Wave Action Design Technique with Minimal Cost on a Turbocharged Engine Equipped with Water Cooled Charge Air Cooler Aimed for Energy Management , 2013 .

[16]  Yung-Cheol Byun,et al.  An Adaptive Stopping Criterion for Backpropagation Learning in Feedforward Neural Network , 2014, MUE 2014.

[17]  J. Samuel,et al.  Effect of Variable Length Intake Manifold on a Turbocharged Multi-Cylinder Diesel Engine , 2013 .

[18]  Wijitha Senadeera,et al.  An artificial neutral network (ANN) model for predicting biodiesel kinetic viscosity as a function of temperature and chemical compositions , 2013 .

[19]  Guillaume Colin,et al.  Neural Model for Real-Time Engine Volumetric Efficiency Estimation , 2013 .

[20]  Adem Çiçek,et al.  Predictive modeling of performance of a helium charged Stirling engine using an artificial neural network , 2013 .

[21]  Fengjun Yan,et al.  Control of diesel engine dual-loop EGR air-path systems by a singular perturbation method , 2013 .

[22]  Pascal Chesse,et al.  Frequency based approach for simulating pressure waves at the inlet of internal combustion engines using a parameterized model , 2013 .

[23]  L Kocher,et al.  Physically based volumetric efficiency model for diesel engines utilizing variable intake valve actuation , 2012 .

[24]  B. Johansson,et al.  Investigation of Performance and Emission Characteristics of a Heavy Duty Natural Gas Engine Operated with Pre-Chamber Spark Plug and Dilution with Excess Air and EGR , 2012 .

[25]  Riccardo Scattolini,et al.  Modelling the volumetric efficiency of ic engines: Parametric, non-parametric and neural techniques , 1996 .

[26]  T. Cerri,et al.  1D simulation of a turbocharged Diesel engine with comparison of short and long EGR route solutions , 2013 .

[27]  Fuwu Yan,et al.  Artificial neural network applications in the calibration of spark-ignition engines: An overview , 2016 .

[28]  Duncan Fyfe Gillies,et al.  Overfitting in linear feature extraction for classification of high-dimensional image data , 2016, Pattern Recognit..

[29]  Adam P. Piotrowski,et al.  A comparison of methods to avoid overfitting in neural networks training in the case of catchment runoff modelling , 2013 .

[30]  Sepp Hochreiter,et al.  The Vanishing Gradient Problem During Learning Recurrent Neural Nets and Problem Solutions , 1998, Int. J. Uncertain. Fuzziness Knowl. Based Syst..

[31]  Günther Palm,et al.  Learning long-term dependencies in segmented-memory recurrent neural networks with backpropagation of error , 2014, Neurocomputing.

[32]  Carlos Guardiola,et al.  Air mass flow estimation in turbocharged diesel engines from in-cylinder pressure measurement , 2010 .

[33]  Marco Sorrentino,et al.  RECURRENT NEURAL NETWORKS FOR AIR-FUEL RATIO ESTIMATION AND CONTROL IN SPARK-IGNITED ENGINES , 2008 .

[34]  P. Baskar,et al.  Effects of oxygen enriched combustion on pollution and performance characteristics of a diesel engine , 2016 .

[35]  Keith Glover,et al.  Model based approach to closed loop control of 1-D engine simulation models , 2014 .

[36]  Igor V. Tetko,et al.  Neural network studies, 1. Comparison of overfitting and overtraining , 1995, J. Chem. Inf. Comput. Sci..

[37]  Abdullah Uzun,et al.  Air mass flow estimation of diesel engines using neural network , 2014 .